mercurial/admin_commands.py

update: add a Rust fast-path when updating from null (and clean)

This case is easy to detect and we have all we need to generate a valid
working copy and dirstate entirely in Rust, which speeds things up
considerably:

On my machine updating a repo of ~300k files goes from 10.00s down to 4.2s,
all while consuming 50% less system time, with all caches hot.
Something to note is that further improvements will probably happen
with the upcoming `InnerRevlog` series that does smarter
mmap hanlding, especially for filelogs.

Here are benchmark numbers on a machine with only 4 cores (and no SMT enabled)

```
### data-env-vars.name               = heptapod-public-2024-03-25-ds2-pnm
  # benchmark.name                   = hg.command.update
  # bin-env-vars.hg.py-re2-module    = default
  # bin-env-vars.hg.changeset.node   = <this change>
  # benchmark.variants.atomic-update = no
  # benchmark.variants.scenario      = null-to-tip
  # benchmark.variants.worker        = default
default: 5.328762  ~~~~~
rust: 1.308654  (-75.44%, -4.02)
### data-env-vars.name               = mercurial-devel-2024-03-22-ds2-pnm
  # benchmark.name                   = hg.command.update
  # bin-env-vars.hg.py-re2-module    = default
  # bin-env-vars.hg.changeset.node   = <this change>
  # benchmark.variants.atomic-update = no
  # benchmark.variants.scenario      = null-to-tip
  # benchmark.variants.worker        = default
default: 1.693271  ~~~~~
rust: 1.151053  (-32.02%, -0.54)
### data-env-vars.name               = mozilla-unified-2024-03-22-ds2-pnm
  # benchmark.name                   = hg.command.update
  # bin-env-vars.hg.py-re2-module    = default
  # bin-env-vars.hg.changeset.node   = <this change>
  # benchmark.variants.atomic-update = no
  # benchmark.variants.scenario      = null-to-tip
  # benchmark.variants.worker        = default
default: 38.901613  ~~~~~
rust: 11.637880 (-70.08%, -27.26)
### data-env-vars.name               = netbsd-xsrc-public-2024-09-19-ds2-pnm
  # benchmark.name                   = hg.command.update
  # bin-env-vars.hg.py-re2-module    = default
  # bin-env-vars.hg.changeset.node   = <this change>
  # benchmark.variants.atomic-update = no
  # benchmark.variants.scenario      = null-to-tip
  # benchmark.variants.worker        = default
default: 4.793727  ~~~~~
rust: 1.505905  (-68.59%, -3.29)
```

# admin_commands.py - command processing for admin* commands
#
# Copyright 2022 Mercurial Developers
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import annotations

from .i18n import _
from .admin import chainsaw, verify
from . import error, registrar, transaction


table = {}
table.update(chainsaw.command._table)
command = registrar.command(table)


@command(
    b'admin::verify',
    [
        (b'c', b'check', [], _(b'add a check'), _(b'CHECK')),
        (b'o', b'option', [], _(b'pass an option to a check'), _(b'OPTION')),
    ],
    helpcategory=command.CATEGORY_MAINTENANCE,
)
def admin_verify(ui, repo, **opts):
    """verify the integrity of the repository

    Alternative UI to `hg verify` with a lot more control over the
    verification process and better error reporting.
    """

    if not repo.url().startswith(b'file:'):
        raise error.Abort(_(b"cannot verify bundle or remote repos"))

    if transaction.has_abandoned_transaction(repo):
        ui.warn(_(b"abandoned transaction found - run hg recover\n"))

    checks = opts.get("check", [])
    options = opts.get("option", [])

    funcs = verify.get_checks(repo, ui, names=checks, options=options)

    ui.status(_(b"running %d checks\n") % len(funcs))
    # Done in two times so the execution is separated from the resolving step
    for name, func in sorted(funcs.items(), key=lambda x: x[0]):
        ui.status(_(b"running %s\n") % name)
        errors = func()
        if errors:
            ui.warn(_(b"found %d errors\n") % errors)